© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51026
    Prev
    Next
    INDEX
    Explanations

    previously awarded, purchased, asked, reported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¥åIJİ
    -0.10
    åı¯æĢľ
    -0.09
     Assassin
    -0.09
    çļĤ
    -0.09
    ë§ŀ
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.08
    缮åīį为æŃ¢
    -0.08
    çİ°åľ¨å·²ç»ı
    -0.08
    ì§ľ
    -0.08
    \Abstract
    -0.08
    POSITIVE LOGITS
    usz
    0.09
    izr
    0.08
    hin
    0.08
     Forbes
    0.08
    éĢļãĤĬ
    0.08
    itan
    0.08
    edy
    0.08
    amac
    0.08
    说è¿ĩ
    0.08
    Await
    0.08
    Activations Density 0.026%

    No Known Activations